Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Gramatika: Jurnal Penelitian Pendidikan Bahasa dan Sastra Indonesia
Reny Nur Eriyani
Universitas Negeri Jakarta
Humanities Languange, Linguistic, Communication & Media

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
VERICULTURA-AI: TOWARD A CULTURALLY GROUNDED AND ETHICALLY RESPONSIVE MULTIMODAL AI FRAMEWORK FOR LIE DETECTION IN INDONESIA Fernandes Arung; Fathiaty Murtadho; Endry Boeriswaty; Reny Nur Eriyani; Hestiyani Parai
Jurnal Gramatika Vol 12, No 1 (2026): Spring Issue (April-September)
Publisher : Universitas PGRI Sumatera Barat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22202/jg.2026.v12i1.10681

Abstract

This study proposes VeriCultura-AI, a culturally grounded blueprint for an artificial intelligence– based lie-detection system that reflects Indonesia’s linguistic, cultural, and social diversity. Addressing long-standing concerns that conventional lie-detection technologies are culturally biased and largely grounded in Western behavioral norms, this research adopts a Research and Development approach using the ADDIE model to design and validate a multimodal system integrating four analytical dimensions: language, culture, voice frequency, and visual gestures. Expert validation by specialists in linguistics, cultural studies and information technology shows a high degree of technical feasibility and conceptual coherence. However, the results also show important gaps in the operationalization of culture, especially in terms of indirect communication styles, multilingual practices and minority cultural representation. VeriCultura-AI aims to mitigate the risk of misclassification and algorithmic bias disproportionately affecting collectivist and minority groups by integrating culture as a core component of AI decision-making, rather than simply a contextual factor. Although this research is confined to validation at the blueprint level and does not include empirical performance testing, it lays an interdisciplinary groundwork for the development of socially and culturally responsive AI. VeriCultura-AI is the first step toward making AI systems that are not only technically strong but also culturally smart and fair.
Co-Authors Endry Boeriswaty Fathiaty Murtadho Fernandes Arung Hestiyani Parai